Sensitivity analyses in longitudinal clinical trials via distributional imputation

Abstract

Missing data is inevitable in longitudinal clinical trials. Conventionally, the missing at random assumption is assumed to handle missingness, which however is unverifiable empirically. Thus, sensitivity analyses are critically important to assess the robustness of the study conclusions against untestable assumptions. Toward this end, regulatory agencies and the pharmaceutical industry use sensitivity models such as return-to-baseline, control-based, and washout imputation, following the ICH E9(R1) guidance. Multiple imputation is popular in sensitivity analyses; however, it may be inefficient and result in an unsatisfying interval estimation by Rubin’s combining rule. We propose distributional imputation in sensitivity analysis, which imputes each missing value by samples from its target imputation model given the observed data. Drawn on the idea of Monte Carlo integration, the distributional imputation estimator solves the mean estimating equations of the imputed dataset. It is fully efficient with theoretical guarantees. Moreover, we propose weighted bootstrap to obtain a consistent variance estimator, taking into account the variabilities due to model parameter estimation and target parameter estimation. The superiority of the distributional imputation framework is validated in the simulation study and an antidepressant longitudinal clinical trial.

Keywords

Longitudinal clinical trial missing data distributional imputation multiple imputation sensitivity analysis

Get full access to this article

View all access options for this article.

References

ICH. E9(R1) statistical principles for clinical trials: addendum: estimands and sensitivity analysis in clinical trials. FDA Guidance Documents 2021.

Rubin

. Inference and missing data. Biometrika 1976; 63: 581–592.

Carpenter

Roger

Kenward

. Analysis of longitudinal trials with protocol deviation: a framework for relevant, accessible assumptions, and inference via multiple imputation. J Biopharm Stat 2013; 23: 1352–1371.

Little

D’Agostino

Cohen

, et al. The prevention and treatment of missing data in clinical trials. N Engl J Med 2012; 367: 1355–1360.

Scharfstein

Rotnitzky

Robins

. Adjusting for nonignorable drop-out using semiparametric nonresponse models. J Am Stat Assoc 1999; 94: 1096–1120.

Robins

Rotnitzky

Scharfstein

. Sensitivity analysis for selection bias and unmeasured confounding in missing data and causal inference models. In Statistical models in epidemiology, the environment, and clinical trials. Springer, 2000. pp. 1–94.

Yin

Shi

. Simulation-based sensitivity analysis for non-ignorably missing data. Stat Methods Med Res 2019; 28: 289–308.

Steenland

Greenland

. Monte Carlo sensitivity analysis and Bayesian analysis of smoking as an unmeasured confounder in a study of silica and lung cancer. Am J Epidemiol 2004; 160: 384–392.

Little

. Pattern-mixture models for multivariate incomplete data. J Am Stat Assoc 1993; 88: 125–134.

10.

Little

Wang

. Pattern-mixture models for multivariate incomplete data with covariates. Biometrics 1996; 52: 98–111.

11.

Cro

Morris

Kenward

, et al. Sensitivity analysis for clinical trials with missing continuous outcome data using controlled multiple imputation: a practical guide. Stat Med 2020; 39: 2815–2842.

12.

US Food and Drug Administration. Statistical review and evaluation of tresiba and ryzodeg 70/30, 2016. https://www.fda.gov/media/102782/download.

13.

Mehrotra

Liu

Permutt

. Missing data in clinical trials: control-based mean imputation and sensitivity analysis. Pharm Stat 2017; 16: 378–392.

14.

Zhang

Golm

Liu

. A likelihood-based approach for the analysis of longitudinal clinical trials with return-to-baseline imputation. Stat Biosci 2020; 12: 23–36.

15.

Rubin

. Multiple imputation for nonresponse in surveys. 81, New York: John Wiley & Sons, 2004.

16.

Meng

. Multiple-imputation inferences with uncongenial sources of input. Stat Sci 1994; 10: 538–558.

17.

Robins

Wang

. Inference for imputation estimators. Biometrika 2000; 87: 113–124.

18.

Yang

Kim

. A note on multiple imputation for method of moments estimation. Biometrika 2016; 103: 244–251.

19.

Liu

Pang

. On analysis of longitudinal clinical trials with missing data using reference-based imputation. J Biopharm Stat 2016; 26: 924–936.

20.

Lepage

. A new algorithm for adaptive multidimensional integration. J Comput Phys 1978; 27: 192–203.

21.

Mallinckrodt

Roger

Chuang-Stein

, et al. Recent developments in the prevention and treatment of missing data. Ther Innov Regul Sci 2014; 48: 68–80.

22.

Roussel

Duran-García

Zhang

, et al. Double-blind, randomized clinical trial comparing the efficacy and safety of continuing or discontinuing the dipeptidyl peptidase-4 inhibitor sitagliptin when initiating insulin glargine therapy in patients with type 2 diabetes: The composit-i study. Diabetes Obes Metab 2019; 21: 781–790.

23.

Yang

Zhang

. Multiply robust matching estimators of average and quantile treatment effects. Scand J Stat 2020; 49: 1–31.

24.

Mallinckrodt

Molenberghs

Lipkovich

et al. Estimands, estimators and sensitivity analysis in clinical trials. London: Chapman and Hall/CRC, 2019.

25.

Zhang

Zimmer

, et al. Missing data imputation with baseline information in longitudinal clinical trials. Stat Biopharm Res 2022; 14: 242–248.

26.

US Food and Drug Administration. Statistical review and evaluation of praluent (alirocumab), 2018. https://www.accessdata.fda.gov/drugsatfda˙docs/nda/2018/125559Orig1s014StatR.pdf.

27.

Mallinckrodt

Bell

Liu

, et al. Aligning estimators with estimands in clinical trials: putting the ich e9 (r1) guidelines into practice. Ther Innov Regul Sci 2020; 54: 353–364.

28.

Hughes

Sterne

Tilling

. Comparison of imputation variance estimators. Stat Methods Med Res 2016; 25: 2541–2557.

29.

Louis

. Finding the observed information matrix when using the em algorithm. J R Stat Soc: Ser B (Methodological) 1982; 44: 226–233.

30.

Tsiatis

. Semiparametric theory and missing data. New York: Springer Science & Business Media, 2007.

31.

Zhang

Chen

Troendle

, et al. Causal inference on quantiles with an obstetric application. Biometrics 2012; 68: 697–706.

32.

Friedman

Hastie

Tibshirani

, et al. The elements of statistical learning, volume 1. Springer series in statistics, New York, 2001.

33.

Kim

. Parametric fractional imputation for missing data analysis. Biometrika 2011; 98: 119–132.

34.

Yang

Kim

. Fractional imputation in survey sampling: a comparative review. Stat Sci 2016; 31: 415–432.

35.

Geweke

. Bayesian inference in econometric models using monte carlo integration. Econometrica: J Economet Soc 1989; 1: 1317–1339.

36.

Boos

Stefanski

. Essential statistical inference: theory and methods. 120, New York: Springer Science & Business Media, 2013.

37.

Tang

. Controlled pattern imputation for sensitivity analysis of longitudinal binary and ordinal outcomes with nonignorable dropout. Stat Med 2018; 37: 1467–1481.

38.

Yang

Zhang

Liu

, et al. SMIM: a unified framework of survival sensitivity analysis using multiple imputation and martingale. Biometrics 2021; 77: 1–11. DOI: 10.1111/biom.13555.

39.

Guan

Yang

. A unified framework for causal inference with multiple imputation using martingale. arXiv preprint arXiv:191104663 2019.

40.

Schafer

. Analysis of incomplete multivariate data. London: CRC Press, 1997.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.42 MB